ConvFormer3D-TAP: Phase/Uncertainty-Aware Front-End Fusion for Cine CMR View Classification Pipelines

• URL: http://arxiv.org/abs/2604.11389v1
• Date: Mon, 13 Apr 2026 12:29:16 GMT
• Title: ConvFormer3D-TAP: Phase/Uncertainty-Aware Front-End Fusion for Cine CMR View Classification Pipelines
• Abstract summary: ConvFormer3D-TAP integrates 3D convolutional tokenization with multiscale self-attention to enhance robustness across cardiac phases and ambiguous temporal segments.<n>On a cohort of 150,974 clinically acquired cine sequences, ConvFormer3D- achieved 96% validation accuracy with per-class F1-scores.<n>These results support ConvFormer3DTAP as a scalable front-end for view routing, filtering and quality control in end-to-end cMRI.
• Score: 0.879504058268139
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reliable recognition of standard cine cardiac MRI views is essential because each view determines which cardiac anatomy is visualized and which quantitative analyses can be performed. Incorrect view identification, whether by a human reader or an automated deep learning system, can propagate errors into segmentation, volumetric assessment, strain analysis, and valve evaluation. However, accurate view classification remains challenging under routine clinical variability in scanner vendor, acquisition protocol, motion artifacts, and plane prescription. We present ConvFormer3D-TAP, a cine-specific spatiotemporal architecture that integrates 3D convolutional tokenization with multiscale self-attention. The model is trained using masked spatiotemporal reconstruction and uncertainty-weighted multi-clip fusion to enhance robustness across cardiac phases and ambiguous temporal segments. The design captures complementary cues: local anatomical structure through convolutional priors and long-range cardiac-cycle dynamics through hierarchical attention. On a cohort of 150,974 clinically acquired cine sequences spanning six standard cine cardiac MRI views, ConvFormer3D-TAP achieved 96% validation accuracy with per-class F1-scores >= 0.94 and strong calibration (ECE = 0.025; Brier = 0.040). Error analysis shows that residual confusions are concentrated in anatomically adjacent long-axis and LVOT/AV view pairs, consistent with intrinsic prescription overlap. These results support ConvFormer3D-TAP as a scalable front-end for view routing, filtering and quality control in end-to-end cMRI workflows.

Related papers

• CMRVision: A Foundation Model for Cardiac MR Image Analysis [21.180056139848528]
  We introduce CMRVision, a CMR-specific foundation model trained using DINOv3-style self-supervised learning.<n>CMRVision is evaluated on two downstream tasks: multi-task segmentation across cine, late gadolinium enhancement (LGE) and mapping sequences.<n>Our experiments show that CMR-specific pretraining, smaller patch sizes, and patch-level objectives consistently improve downstream performance.
  arXiv  Detail & Related papers  (2026-09-01T14:34:30Z)
• How Good are Foundation Models in Longitudinal MRI Disease Progression Reasoning? [49.14050864978079]
  We introduce the Time-Aware Multi-View MRI Benchmark, an evaluation framework unifying multi-view anatomical input, temporal reasoning, and structured localization guidance.<n>The benchmark comprises 3,920 expert-verified question-answer pairs derived from 890 patients across over 3,200 longitudinal MRI timepoints.
  arXiv  Detail & Related papers  (2026-08-13T14:35:20Z)
• From Raw Segmentations to Simulation-Ready Cardiac Meshes: An Automated Framework for Anatomical Reconstruction and Virtual Cohort Generation [40.52388056968461]
  We present a semi-automatic pipeline that converts CT-based segmentations into simulation-ready cardiac meshes.<n>A Chamfer-distance morphing strategy deforms a high-quality template toward each segmented heart, matching individual chambers while preserving topology.<n>The pipeline is validated on 58 healthy cardiac CT scans, including all cardiac chambers and proximal vessel segments.
  arXiv  Detail & Related papers  (2026-06-29T09:07:05Z)
• Cross-View Attention Fusion Net: A Prior-Guided Dual-View Representation Learning for Cardiac Output Estimation from Short-Term PPG Signals [4.906669147334531]
  Cross-View Fusion Network (CVAF-Net) is a prior-guided dual-view deep learning model for CO estimation from short, fixed-length PPG segments.<n>CVAF-Net processes raw PPG as a temporal view and a feature sequence map (FSM) as a structured prior-guided view, and fuses the two representations through cross-view attention.
  arXiv  Detail & Related papers  (2026-05-19T10:59:49Z)
• VISTA: Validation-Guided Integration of Spatial and Temporal Foundation Models with Anatomical Decoding for Rare-Pathology VCE Event Detection [39.50945484737978]
  We formulate the RARE-VISION task as a metric-aligned event detection problem instead of a purely frame-wise classification task.<n>Our framework combines two complementary backbones, EndoFM-LV for local temporal context and DINOv3 ViT-L/16 for strong frame-level visual semantics.<n> validation ablations indicate that complementary backbones, validation-guided fusion, and anatomy-aware temporal decoding all contribute to event-level performance.
  arXiv  Detail & Related papers  (2026-03-18T23:01:12Z)
• EchoLVFM: One-Step Video Generation via Latent Flow Matching for Echocardiogram Synthesis [1.703077957571322]
  We introduce EchoLVFM, a one-step latent video flow-matching framework for controllable echocardiogram generation.<n> operating in the latent space, EchoLVFM synthesises temporally coherent videos in a single inference step.<n>Results demonstrate competitive video quality, strong EF adherence, and 57.9% discrimination accuracy by expert clinicians.
  arXiv  Detail & Related papers  (2026-03-14T14:39:09Z)
• Enabling Ultra-Fast Cardiovascular Imaging Across Heterogeneous Clinical Environments with a Generalist Foundation Model and Multimodal Database [64.65360708629485]
  MMCMR-427K is the largest and most comprehensive multimodal cardiovascular magnetic resonance k-space database.<n> CardioMM is a reconstruction foundation model capable of adapting to heterogeneous fast CMR imaging scenarios.<n> CardioMM unifies semantic contextual understanding with physics-informed data consistency to deliver robust reconstructions.
  arXiv  Detail & Related papers  (2025-12-25T12:47:50Z)
• Anatomically Constrained Transformers for Echocardiogram Analysis [38.280536446335056]
  ViACT represents a deforming anatomical structure as a point set and encodes both its spatial geometry and corresponding image patches into transformer tokens.<n>During pre-training, ViACT follows a masked autoencoding strategy that masks and reconstructs only anatomical patches.<n>ViACTs generalize to myocardium point tracking without requiring task-specific components.
  arXiv  Detail & Related papers  (2025-11-02T22:52:30Z)
• Automated Labeling of Intracranial Arteries with Uncertainty Quantification Using Deep Learning [2.6279333406008476]
  We present a deep learning-based framework for automated artery labeling from 3D Time-of-Flight Magnetic Resonance Angiography (3D ToF-MRA)<n>Our framework offers a scalable, accurate, and uncertainty-aware solution for automated cerebrovascular labeling, supporting downstream hemodynamic analysis and facilitating clinical integration.
  arXiv  Detail & Related papers  (2025-09-22T12:57:21Z)
• LGE-Guided Cross-Modality Contrastive Learning for Gadolinium-Free Cardiomyopathy Screening in Cine CMR [51.11296719862485]
  We propose a Contrastive Learning and Cross-Modal alignment framework for gadolinium-free cardiomyopathy screening using cine CMR sequences.<n>By aligning the latent spaces of cine CMR and Late Gadolinium Enhancement (LGE) sequences, our model encodes fibrosis-specific pathology into cine CMR embeddings.
  arXiv  Detail & Related papers  (2025-08-23T07:21:23Z)
• Depth-Sequence Transformer (DST) for Segment-Specific ICA Calcification Mapping on Non-Contrast CT [38.85617601239779]
  Conventional 3D models are forced to process downsampled volumes or isolated patches.<n>We reformulate the 3D challenge as a textbfParallel Probabilistic Landmark localization task along the 1D axial dimension.<n>We propose the textbfDepth-Sequence Transformer (DST), a framework that processes full-resolution CT volumes as sequences of 2D slices.
  arXiv  Detail & Related papers  (2025-07-10T23:12:12Z)
• Myocardial Region-guided Feature Aggregation Net for Automatic Coronary artery Segmentation and Stenosis Assessment using Coronary Computed Tomography Angiography [13.885760158090692]
  Myocardial Region-guided Feature Aggregation Net is a novel U-shaped dual-encoder architecture that integrates anatomical prior knowledge to enhance robustness in coronary artery segmentation.<n>Our framework incorporates three key innovations: (1) a Myocardial Region-guided Module that directs attention to coronary regions via bridging expansion and multi-scale feature fusion, (2) a Residual Feature Extraction Module that combines parallel spatial channel attention with residual blocks to enhance local-global feature discrimination, and (3) a Multi-scale Feature Fusion Module for adaptive aggregation of hierarchical vascular features.
  arXiv  Detail & Related papers  (2025-04-27T16:43:52Z)
• Successive Subspace Learning for Cardiac Disease Classification with Two-phase Deformation Fields from Cine MRI [36.044984400761535]
  This work proposes a lightweight successive subspace learning framework for CVD classification. It is based on an interpretable feedforward design, in conjunction with a cardiac atlas. Compared with 3D CNN-based approaches, our framework achieves superior classification performance with 140$times$ fewer parameters.
  arXiv  Detail & Related papers  (2023-01-21T15:00:59Z)
• Automated Quality Controlled Analysis of 2D Phase Contrast Cardiovascular Magnetic Resonance Imaging [2.189751467114811]
  Flow analysis carried out using phase contrast cardiac magnetic resonance imaging (PC-CMR) We propose a novel deep learning based framework for the fully-automated analysis of flow from full CMR scans.
  arXiv  Detail & Related papers  (2022-09-28T16:37:35Z)
• Spatio-temporal Multi-task Learning for Cardiac MRI Left Ventricle Quantification [6.887389908965403]
  We propose a learning-temporal multi-task approach to obtain a complete set of measurements of cardiac left ventricle (LV) morphology. We first segment LVs using an encoder-decoder network and then introduce a framework to regress 11 LV indices and classify the cardiac phase. The proposed model is based on the 3D-temporal convolutions, which extract spatial and features from MR images.
  arXiv  Detail & Related papers  (2020-12-24T17:48:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.